A Stanford paper introduces the Collaborative Intelligence Benchmark to measure the collaborative abilities of AI agents as teammates
A paper from Stanford and other institutions introduces the Collaborative Intelligence Benchmark, which measures AI agents as teammates using 240 tasks across eight team collaboration dimensions, with individual scoring to isolate personal capabilities.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original